Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add arctan303/creator.skill --skill dev-buildergit clone --depth 1 https://github.com/arctan303/creator.skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/arctan303/creator.skill/dev-builder)<a href="https://agentmods.dev/skills/arctan303/creator.skill/dev-builder"><img src="https://agentmods.dev/badge/skills/arctan303/creator.skill/dev-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arctan303/creator.skill/dev-builder"><img src="https://agentmods.dev/badge/skills/arctan303/creator.skill/dev-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.00586 |
| Opus 5.5 | $0.00014 | $0.00234 |
| Sonnet 5.5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
dev-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
开发实施
Purpose
完成最小完整变更，证明可观察行为并留下下一会话所需的当前事实。
Trigger
目标、预期行为、范围和验收足够明确；可以是产品短任务、Phase 或非诊断型维护。
Required context
现状入口、有效需求/设计、相关任务或 Phase、工作区修改、验证入口和授权；只读相关材料。
Workflow
- 确认路线、规模和具体影响。符合 Phase 条件却缺计划时先补计划，其余短任务直接执行。
- 核对代码与他人修改，按当前有效契约实施；新决定替代旧规则时先对账，不以代码差异静默改需求。
- 用针对性行为检查验证；必要构建/测试通过后，有新变更、失败或疑点才重复。
- 验证后更新受影响现状、需求状态、设计和计划；无影响的入口不机械刷新。
- 按任务可分离性与收益选择有边界的子代理，明确文件归属并由主会话集成；风险决定独立审查而非是否可委派。R0/R1 不自动审查；轻量维护进入 batch.md，小型产品变更保留需求/短任务。R2 使用 fresh reviewer，尊重用户/宿主限制。
- 聚焦处理审查发现，有实质修复可再复核，无进展或资源预算用尽时保存恢复检查点。
- 在安全收尾点使用 project-knowledge 沉淀明确项目准则和受影响现状；撤销能力时关闭失效任务及测试义务，不能把历史未验收项重新列为待办。完成整个已授权目标和必要集成后交接，不因一个子任务结束提前退出。
Output
实现结果、相关契约与文件、验证结果及适用基线、更新的文档、按需拆分的实施/验证/审查/发布状态和下一步。
Stop or escalate
未知正确行为影响方案时只暂停相关部分。不能以验证缺口代替完成，也不能因为工具失败或多个文件就自动升 R2。外部动作按已有明确授权边界执行。
References
交付时读 stage-contract.md；文档、队列及审查细则读共同契约。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed · +1 lines · -26 tokens per session 9c69b32b7350
- 1mo ago Changed · -17 lines · -11 tokens per session e8b1586e791f
- 1mo ago First seen · 57 lines · 71 tokens per session scan A b5877b877b08
dev-builder is a skill published in the GitHub repository arctan303/creator.skill (19 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 586 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.